© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 22578
    Prev
    Next
    INDEX
    Explanations

    words related to organized events or gatherings

    oai_token-act-pair · gpt-3.5-turbo

    references to significant events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aves
    -0.66
    iencies
    -0.66
    ben
    -0.64
    icides
    -0.63
    BuyableInstoreAndOnline
    -0.63
    ldon
    -0.63
    ernels
    -0.62
    agall
    -0.61
    sheets
    -0.61
     grades
    -0.61
    POSITIVE LOGITS
     event
    3.62
     Event
    2.57
     EVENT
    2.49
    event
    2.49
     events
    2.43
    Event
    2.22
     Events
    2.08
    events
    2.02
    Events
    1.78
     festival
    1.44
    Activations Density 0.019%

    No Known Activations